ggpubr, gapminder, tax highlight plots

1 ggpubr

1.1 options & settings

For scrollable output

options(scipen = 999)

1.2 Source

http://www.sthda.com/english/articles/24-ggpubr-publication-ready-plots/ https://youtu.be/NJquUKavAOI https://youtu.be/UvRaNJC05Ec

1.3 Loading libs

# install.packages("gapminder")

library(tidyverse)
library(ggpubr)
library(gapminder)

1.4 creating theme_viny_bright

theme_viny_bright <- function(){
  
  library(ggthemes)
  
  ggthemes::theme_fivethirtyeight() %+replace%
  
  theme(
    axis.title = element_text(),
    
    axis.text = element_text(size = 13),
    
    legend.text = element_text(size = 10),
    
    panel.background = element_rect(fill = "white"),
    
    plot.background = element_rect(fill = "white"),
    
    strip.background = element_blank(),
    
    legend.background = element_rect(fill = NA),
    
    legend.key = element_rect(fill = NA),

    plot.title = element_text(hjust = 0.5,
                              size = 19,
                              face = "bold"),
    plot.subtitle = element_text(hjust = 0.5, colour = "maroon")
      )
  
  }

1.5 Loading gapminder lib data

gapminder %>% head()

gapminder %>% glimpse()

Rows: 1,704
Columns: 6
$ country   <fct> Afghanistan, Afghanistan, Afghanistan, Afghanistan, Afghanistan, Afghanistan, Afgh...
$ continent <fct> Asia, Asia, Asia, Asia, Asia, Asia, Asia, Asia, Asia, Asia, Asia, Asia, Europe, Eu...
$ year      <int> 1952, 1957, 1962, 1967, 1972, 1977, 1982, 1987, 1992, 1997, 2002, 2007, 1952, 1957...
$ lifeExp   <dbl> 28.801, 30.332, 31.997, 34.020, 36.088, 38.438, 39.854, 40.822, 41.674, 41.763, 42...
$ pop       <int> 8425333, 9240934, 10267083, 11537966, 13079460, 14880372, 12881816, 13867957, 1631...
$ gdpPercap <dbl> 779.4453, 820.8530, 853.1007, 836.1971, 739.9811, 786.1134, 978.0114, 852.3959, 64...

attach(gapminder)

1.5.1 Boxplot within Violin & more

violin_plot1 <- gapminder %>% filter(year == max(year)) %>% 
  
  ggpubr::ggviolin(., x = "continent", y = "gdpPercap", 
                   fill = "continent", color = "continent", 
                   add = "boxplot", add.params = list(fill = "white", shape = "continent"))

set_palette(violin_plot1, palette = "jco")

violin_plot2 <- gapminder %>% filter(year == max(year)) %>% 
  
  ggpubr::ggviolin(., x = "continent", y = "gdpPercap", 
                   color = "continent", 
                   add = "point")

set_palette(violin_plot2, palette = "jco")

violin_plot3 <- gapminder %>% filter(year == max(year)) %>% 
  
  ggpubr::ggviolin(., x = "continent", y = "gdpPercap", 
                   color = "continent", 
                   add = "point")

set_palette(violin_plot3, palette = "jco")

violin_plot4 <- gapminder %>% filter(year == max(year)) %>% 
  
  ggpubr::ggviolin(., x = "continent", y = "gdpPercap", 
                   color = "continent", 
                   add = "jitter")

set_palette(violin_plot4, palette = "jco")

1.6 Loading latest gapminder data

gapminder_new <- read_csv("E:/3. R/gapminder data/income - gdppercap/gdppercapita_us_inflation_adjusted.csv")

head(gapminder_new)

dim(gapminder_new)

[1] 191  61

gapminder_new %>% select(country,"2010","2014","2017","2019") %>% head()

gap_longer <- gapminder_new %>% 
  pivot_longer(cols = !country, names_to = "year", values_to = "gdpPercap") 

gap_longer %>% head()

dim(gap_longer)

[1] 11460     3

gap_longer <- gap_longer %>% mutate(year = as.integer(year))

gap_longer %>% filter(year == max(year)) 

gap_longer %>% filter(year == max(year)) %>% count(country)

gap_longer %>% filter(year == max(year)) %>% count(country) %>% filter(n > 1)

gapminder %>% group_by(country, continent) %>% count()

gap_longer <- left_join(x = gap_longer, 
             y = gapminder %>% 
               group_by(country, continent) %>% 
               count() %>% 
               select(country, continent) ,
             by =  "country") 

gap_longer %>% head()

dim(gap_longer)

[1] 11460     4

gap_longer$continent %>% levels()

[1] "Africa"   "Americas" "Asia"     "Europe"   "Oceania" 

gap_longer %>% filter(is.na(continent)) %>% select(country) %>% unique() %>%  head()

fill_continents_df <- data.frame(
  
  country = c("Andorra", "Antigua and Barbuda", "Armenia",              
              "Azerbaijan", "Bahamas", "Barbados", "Belarus", 
              "Belize", "Bhutan",   "Brunei"),

  continent = c("Europe", "Americas", "Europe", "Europe", "Americas", 
                "Americas", "Europe", "Americas", "Asia", "Asia")
)

fill_continents_df

NA

top_30 <- gap_longer %>% 
  filter(!is.na(continent), year %in% c(2019)) %>% 
  top_n(n = 30, wt = gdpPercap) %>% 
  arrange(gdpPercap)

top_30 %>%  head()

1.6.1 Publish ready bar plots

Plot from: http://www.sthda.com/english/articles/24-ggpubr-publication-ready-plots/

ggbarplot(top_30, x = "country", y = "gdpPercap", fill = "continent",
          color = "white",
          palette = "jco", 
          sort.val = "desc", 
          sort.by.groups = F, 
          x.text.angle = 90)

ggbarplot(top_30, x = "country", y = "gdpPercap", fill = "continent",
          color = "white",
          palette = "jco", 
          sort.val = "asc", 
          sort.by.groups = T, 
          x.text.angle = 90)

1.6.2 Publish ready lollypop plots

ggdotchart(top_30, x = "country", y = "gdpPercap",
          color = "continent",
          palette = "jco", 
          sort.val = "desc", 
          sort.by.groups = T, 
          add = "segments",
          rotate = TRUE,
          group = "continent",
          dot.size = 6,
          label = top_30$gdpPercap,
          font.label = list(color = "black", size = 12, vjust = 0.5, hjust = -1),
          ggtheme = theme_pubr()
          )

ggdotchart(top_30, x = "country", y = "gdpPercap",
          color = "continent",
          palette = "jco", 
          sorting = "desc", 
          sort.by.groups = T, 
          add = "segments",
          rotate = TRUE,
          group = "continent",
          dot.size = 9,
          label = top_30$gdpPercap,
          font.label = list(color = "black", size = 12, vjust = 0.5, hjust = -1),
          ggtheme = theme_pubr()
          )

from:

https://rpkgs.datanovia.com/ggpubr/reference/ggdotchart.html http://www.sthda.com/english/articles/24-ggpubr-publication-ready-plots/

ggdotchart(top_30, x = "country", y = "gdpPercap",
          color = "continent",
          palette = "jco", 
          sorting = "desc", 
          sort.by.groups = T, 
          add = "segments",
          # rotate = TRUE,
          group = "continent",
          dot.size = 9,
          label = top_30$gdpPercap,
          font.label = list(color = "black", size = 12, vjust = 0.5, hjust = -1),
          ggtheme = theme_pubr(),
          # x.text.col = TRUE
          )

2 Highlight Plots

library(gghighlight)

ggplot(data = gap_longer) +
  geom_line(col = "grey", aes(x = year, y = gdpPercap, group = country)) +
  theme_minimal() +
  theme(axis.text.x = element_text(angle = 90),
        legend.position = "none",
        panel.grid.major = element_blank(),
        panel.grid.minor = element_blank()
          ) +
  scale_x_continuous(breaks = seq(from = 1960, to = 2020, by = 5))

ggplot(data = gap_longer) +
  geom_line(col = "grey", aes(x = year, y = gdpPercap, group = country)) +
  theme_minimal() +
  theme(axis.text.x = element_text(angle = 90),
        legend.position = "none",
        panel.grid.major = element_blank(),
        panel.grid.minor = element_blank()
          ) +
  scale_x_continuous(breaks = seq(from = 1960, to = 2020, by = 5)) +
  scale_y_log10() 

gap_longer %>% 
  mutate(highlight_type = case_when(country %in% 
                                 c("India","Singapore","Malaysia","Norway","Denmark") ~ "Yes",
                               TRUE ~ "No")) %>% 
ggplot() +
  geom_line(aes(x = year, y = gdpPercap, group = country, col = highlight_type)) +
  theme_minimal() +
  theme(axis.text.x = element_text(angle = 90),
        legend.position = "none",
        panel.grid.major = element_blank(),
        panel.grid.minor = element_blank()
          ) +
  scale_x_continuous(breaks = seq(from = 1960, to = 2020, by = 5)) +
  scale_y_log10() +
  scale_colour_manual(values = c("grey", "black")) +
  scale_size_manual(values = c(.5, 7))

gap_longer %>% 
  mutate(highlight_type = case_when(country %in% 
                                 c("India","Singapore","Malaysia","Norway",
                                   "Denmark","United States","United Kingdom") ~ "Yes",
                               TRUE ~ "No")) %>% 
ggplot() +
  geom_line(aes(x = year, y = gdpPercap, group = country, col = country)) +
  theme_minimal() +
  theme(axis.text.x = element_text(angle = 90),
        legend.position = "none",
        panel.grid.major = element_blank(),
        panel.grid.minor = element_blank()
          ) +
  scale_x_continuous(breaks = seq(from = 1960, to = 2020, by = 5)) +
  scale_y_log10() + 
  gghighlight(highlight_type == "Yes") +
  labs(title = "GDP/Capita (Income / Person) in $ of Countries wrt to time",
       caption = "Data Source: Gapminder",
       y = "Log of Income (GDP / Capita)" 
       )

2.0.1 Log scale

gap_longer %>% 
  mutate(highlight_type = case_when(country %in% 
                                 c("India","Singapore","Malaysia","Norway",
                                   "Denmark","United States","United Kingdom","China") ~ "Yes",
                               TRUE ~ "No")) %>% 
ggplot() +
  geom_line(aes(x = year, y = gdpPercap, col = country), size = 1.1) +
  scale_x_continuous(breaks = seq(from = 1960, to = 2020, by = 5)) +
  scale_y_log10(labels = scales::comma) + 
  gghighlight(highlight_type == "Yes",
              unhighlighted_params = list(size = 1, colour = alpha("grey", 0.4))) +
  theme_minimal() +
  theme(axis.text.x = element_text(angle = 90),
        legend.position = "none",
        panel.grid.major = element_blank(),
        panel.grid.minor = element_blank(),
        plot.title = element_text(hjust = 0.5),
        plot.subtitle = element_text(hjust = 0.5, colour = "maroon")
          ) +
  labs(title = "Income(Log of GDP/Capita in $) of world countries across time",
       subtitle = "created by ViSa",
       caption = "Data Source: Gapminder",
       y = "Log of Income (GDP / Capita) i.e Multiplier scale" 
       )

ggsave(filename = "gdpPerCap_log_highlighted_chi.jpg", dpi = 300, height = 8, width = 10)

2.0.2 Facet Log scale

gap_longer %>% 
  mutate(highlight_type = case_when(country %in% 
                                 c("India","Singapore","Malaysia","Norway",
                                   "Denmark","United States","United Kingdom","China") ~ "Yes",
                               TRUE ~ "No")) %>% 
ggplot() +
  geom_line(aes(x = year, y = gdpPercap, col = country), size = 1.1) +
  scale_x_continuous(breaks = seq(from = 1960, to = 2020, by = 5)) +
  scale_y_log10(labels = scales::comma) + 
  gghighlight(highlight_type == "Yes",
              unhighlighted_params = list(size = 1, colour = alpha("grey", 0.4))) +
  facet_wrap(~continent) +
  theme_minimal() +
  theme(axis.text.x = element_text(angle = 90),
        legend.position = "none",
        panel.grid.major = element_blank(),
        panel.grid.minor = element_blank(),
        plot.title = element_text(hjust = 0.5),
        plot.subtitle = element_text(hjust = 0.5, colour = "maroon")
          ) +
  labs(title = "Income(Log of GDP/Capita in $) of world countries based on continents across time",
       subtitle = "created by ViSa",
       caption = "Data Source: Gapminder",
       y = "Log of Income (GDP / Capita) i.e Multiplier scale" 
       )

ggsave(filename = "gdpPerCap_log_highlighted_facet_chi.jpg", dpi = 300, height = 8, width = 10)

2.0.3 Normal scale

gap_longer %>% 
  mutate(highlight_type = case_when(country %in% 
                                 c("India","Singapore","Malaysia","Norway",
                                   "Denmark","United States","United Kingdom","China") ~ "Yes",
                               TRUE ~ "No")) %>% 
ggplot() +
  geom_line(aes(x = year, y = gdpPercap, col = country), size = 1.1) +
  scale_x_continuous(breaks = seq(from = 1960, to = 2020, by = 5)) +
  scale_y_continuous(labels = scales::comma, 
                     breaks = seq(from = 0, to = 200000, by = 25000)) +
  gghighlight(highlight_type == "Yes",
              unhighlighted_params = list(size = 1, colour = alpha("grey", 0.4))) +
  theme_minimal() +
  theme(axis.text.x = element_text(angle = 90),
        legend.position = "none",
        panel.grid.major = element_blank(),
        panel.grid.minor = element_blank(),
        plot.title = element_text(hjust = 0.5),
        plot.subtitle = element_text(hjust = 0.5, colour = "maroon")
          ) +
  labs(title = "Income(GDP/Capita in $) of world countries across time",
       subtitle = "created by ViSa",
       caption = "Data Source: Gapminder",
       y = "Income (GDP / Capita) in $" 
       )

ggsave(filename = "gdpPerCap_norm_highlighted_chi.jpg", dpi = 300, height = 8, width = 10)

2.0.4 Facet Normal scale

gap_longer %>% 
  mutate(highlight_type = case_when(country %in% 
                                 c("India","Singapore","Malaysia","Norway",
                                   "Denmark","United States","United Kingdom","China") ~ "Yes",
                               TRUE ~ "No")) %>% 
ggplot() +
  geom_line(aes(x = year, y = gdpPercap, col = country), size = 1.1) +
  scale_x_continuous(breaks = seq(from = 1960, to = 2020, by = 5)) +
  scale_y_continuous(labels = scales::comma, 
                     breaks = seq(from = 0, to = 200000, by = 25000)) +
  gghighlight(highlight_type == "Yes",
              unhighlighted_params = list(size = 1, colour = alpha("grey", 0.4))) +
  facet_wrap(~continent) +
  theme_minimal() +
  theme(axis.text.x = element_text(angle = 90),
        legend.position = "none",
        panel.grid.major = element_blank(),
        panel.grid.minor = element_blank(),
        plot.title = element_text(hjust = 0.5),
        plot.subtitle = element_text(hjust = 0.5, colour = "maroon")
          ) +
  labs(title = "Income(GDP/Capita in $) of world countries based on continents across time",
       subtitle = "created by ViSa",
       caption = "Data Source: Gapminder",
       y = "Income (GDP / Capita) in $" 
       )

ggsave(filename = "gdpPerCap_norm_highlighted_facet_chi.jpg", dpi = 300, height = 8, width = 10)

2.1 Applying theme_viny_bright

2.1.1 Log scale

gap_longer %>% 
  mutate(highlight_type = case_when(country %in% 
                                 c("India","Singapore","Malaysia","Norway",
                                   "Denmark","United States","United Kingdom","China") ~ "Yes",
                               TRUE ~ "No")) %>% 
ggplot() +
  geom_line(aes(x = year, y = gdpPercap, col = country), size = 1.1) +
  scale_x_continuous(breaks = seq(from = 1960, to = 2020, by = 5)) +
  scale_y_log10(labels = scales::comma) + 
  gghighlight(highlight_type == "Yes",
              unhighlighted_params = list(size = 1, colour = alpha("pink", 0.4))) +
  theme_viny_bright() +
  theme(axis.text.x = element_text(angle = 90)
          ) +
  labs(title = "Income(Log of GDP/Capita in $) of world countries across time",
       subtitle = "created by ViSa",
       caption = "Data Source: Gapminder",
       y = "Log of Income (GDP / Capita) i.e Multiplier scale" 
       )

ggsave(filename = "gdpPerCap_log_highlighted_pink.jpg", dpi = 300, height = 8, width = 10)

2.1.2 Facet Log scale

gap_longer %>% 
  mutate(highlight_type = case_when(country %in% 
                                 c("India","Singapore","Malaysia","Norway",
                                   "Denmark","United States","United Kingdom","China") ~ "Yes",
                               TRUE ~ "No")) %>% 
ggplot() +
  geom_line(aes(x = year, y = gdpPercap, col = country), size = 1.1) +
  scale_x_continuous(breaks = seq(from = 1960, to = 2020, by = 5)) +
  scale_y_log10(labels = scales::comma) + 
  gghighlight(highlight_type == "Yes",
              unhighlighted_params = list(size = 1, colour = alpha("pink", 0.4))) +
  facet_wrap(~continent) +
  theme_viny_bright() +
  theme(axis.text.x = element_text(angle = 90)
          ) +
  labs(title = "Income(Log of GDP/Capita in $) of world countries based on continents across time",
       subtitle = "created by ViSa",
       caption = "Data Source: Gapminder",
       y = "Log of Income (GDP / Capita) i.e Multiplier scale" 
       )

ggsave(filename = "gdpPerCap_log_highlighted_facet_pink.jpg", dpi = 300, height = 8, width = 10)

2.1.3 Normal scale

gap_longer %>% 
  mutate(highlight_type = case_when(country %in% 
                                 c("India","Singapore","Malaysia","Norway",
                                   "Denmark","United States","United Kingdom","China") ~ "Yes",
                               TRUE ~ "No")) %>% 
ggplot() +
  geom_line(aes(x = year, y = gdpPercap, col = country), size = 1.1) +
  scale_x_continuous(breaks = seq(from = 1960, to = 2020, by = 5)) +
  scale_y_continuous(labels = scales::comma, 
                     breaks = seq(from = 0, to = 200000, by = 25000)) +
  gghighlight(highlight_type == "Yes",
              unhighlighted_params = list(size = 1, colour = alpha("pink", 0.4))) +
  theme_viny_bright() +
  theme(axis.text.x = element_text(angle = 90)
          ) +
  labs(title = "Income(GDP/Capita in $) of world countries across time",
       subtitle = "created by ViSa",
       caption = "Data Source: Gapminder",
       y = "Income (GDP / Capita) in $" 
       )

ggsave(filename = "gdpPerCap_norm_highlighted_pink.jpg", dpi = 300, height = 8, width = 10)

2.1.4 Facet Normal scale

gap_longer %>% 
  mutate(highlight_type = case_when(country %in% 
                                 c("India","Singapore","Malaysia","Norway",
                                   "Denmark","United States","United Kingdom","China") ~ "Yes",
                               TRUE ~ "No")) %>% 
ggplot() +
  geom_line(aes(x = year, y = gdpPercap, col = country), size = 1.1) +
  scale_x_continuous(breaks = seq(from = 1960, to = 2020, by = 5)) +
  scale_y_continuous(labels = scales::comma, 
                     breaks = seq(from = 0, to = 200000, by = 25000)) +
  gghighlight(highlight_type == "Yes",
              unhighlighted_params = list(size = 1, colour = alpha("pink", 0.4))) +
  facet_wrap(~continent) +
  theme_viny_bright() +
  theme(axis.text.x = element_text(angle = 90)
          ) +
  labs(title = "Income(GDP/Capita in $) of world countries based on continents across time",
       subtitle = "created by ViSa",
       caption = "Data Source: Gapminder",
       y = "Income (GDP / Capita) in $" 
       )

ggsave(filename = "gdpPerCap_norm_highlighted_facet_pink.jpg", dpi = 300, height = 8, width = 10)

2.2 Loading tax data

2.2.1 Data source:

https://ourworldindata.org/taxation

tax_rev_to_gdp <- read_csv("E:/3. R/ourworldindata.org/total-tax-revenues-gdp.csv")

head(tax_rev_to_gdp)

tax_rev_to_gdp <- tax_rev_to_gdp %>% 
  rename("tax_revnue_perc_of_gdp" = "Total tax revenue (% of GDP) (ICTD (2019))",
         "country" = "Entity",
         "year" = "Year")

head(tax_rev_to_gdp)

Adding continent

tax_rev <- left_join(x = tax_rev_to_gdp,
          y = gapminder %>% 
            group_by(country, continent) %>% 
            count() %>% 
            select(country, continent),
          by = "country"
            )

summary(tax_rev)

   country              Code                year      tax_revnue_perc_of_gdp    continent   
 Length:5318        Length:5318        Min.   :1980   Min.   : 0.08581       Africa  :1309  
 Class :character   Class :character   1st Qu.:1993   1st Qu.:11.63091       Americas: 722  
 Mode  :character   Mode  :character   Median :2002   Median :18.01959       Asia    : 749  
                                       Mean   :2001   Mean   :20.05868       Europe  : 926  
                                       3rd Qu.:2009   3rd Qu.:27.63104       Oceania :  75  
                                       Max.   :2017   Max.   :56.91614       NA's    :1537  

attach(tax_rev)

tax_rev %>% 
  mutate(highlight_type = case_when(country %in%
                                 c("India","Singapore","Malaysia","Norway",
                                   "Denmark","United States","United Kingdom","China") ~ "Yes",
                               TRUE ~ "No")) %>%
ggplot() +
  geom_line(aes(x = year, y = round(tax_revnue_perc_of_gdp,2), col = country), size = 1.1) +
  scale_x_continuous(breaks = seq(from = 1980, to = 2020, by = 5)) +
  scale_y_continuous(#labels = scales::percent,
                     breaks = seq(from = 0, to = 40, by = 5)) +
  gghighlight(highlight_type == "Yes",
              unhighlighted_params = list(size = 1, colour = alpha("grey", 0.4))) +
  # facet_wrap(~continent) +
  theme_minimal() +
  theme(axis.text.x = element_text(angle = 90),
        legend.position = "none",
        panel.grid.major = element_blank(),
        panel.grid.minor = element_blank(),
        plot.title = element_text(hjust = 0.5),
        plot.subtitle = element_text(hjust = 0.5, colour = "maroon")
          ) +
  labs(title = "Total Tax Revenue earned % of GDP for world countries across time",
       subtitle = "created by ViSa",
       caption = "Data Source: Gapminder",
       y = "Total Tax Revenue % of GDP" 
       )

tax_rev %>% 
  mutate(highlight_type = case_when(country %in%
                                 c("India","Singapore","Malaysia","Norway",
                                   "Denmark","United States","United Kingdom","China") ~ "Yes",
                               TRUE ~ "No")) %>%
ggplot() +
  geom_line(aes(x = year, y = round(tax_revnue_perc_of_gdp,2), col = country), size = 1.1) +
  scale_x_continuous(breaks = seq(from = 1980, to = 2020, by = 5)) +
  scale_y_continuous(labels = label_dollar(prefix = "", suffix = " %"),
                     breaks = seq(from = 0, to = 40, by = 5)) +
  gghighlight(highlight_type == "Yes",
              unhighlighted_params = list(size = 1, colour = alpha("grey", 0.4))) +
  facet_wrap(~continent) +
  theme_minimal() +
  theme(axis.text.x = element_text(angle = 90),
        legend.position = "none",
        panel.grid.major = element_blank(),
        panel.grid.minor = element_blank(),
        plot.title = element_text(hjust = 0.5),
        plot.subtitle = element_text(hjust = 0.5, colour = "maroon")
          ) +
  labs(title = "Total Tax Revenue earned % of GDP for world countries across time",
       subtitle = "created by ViSa",
       caption = "Data Source: Gapminder",
       y = "Total Tax Revenue % of GDP" 
       )

Error in label_dollar(prefix = "", suffix = " %") : 
  could not find function "label_dollar"

2.2.2 Applying theme_viny_bright

library(scales)

tax_rev %>% 
  mutate(highlight_type = case_when(country %in%
                                 c("India","Singapore","Malaysia","Norway",
                                   "Denmark","United States","United Kingdom","China") ~ "Yes",
                               TRUE ~ "No")) %>%
ggplot() +
  geom_line(aes(x = year, y = round(tax_revnue_perc_of_gdp,2), col = country), size = 1.1) +
  scale_x_continuous(breaks = seq(from = 1980, to = 2020, by = 5)) +
  scale_y_continuous(labels = label_dollar(prefix = "", suffix = " %"),
                     breaks = seq(from = 0, to = 60, by = 5)) +
  gghighlight(highlight_type == "Yes",
              unhighlighted_params = list(size = 1, colour = alpha("pink", 0.4))) +
  # facet_wrap(~continent) +
  theme_viny_bright() +
  theme(axis.text.x = element_text(angle = 90)
          ) +
  labs(title = "Total Tax Revenue earned % of GDP for world countries across time",
       subtitle = "created by ViSa",
       caption = "Data Source: Gapminder",
       y = "Total Tax Revenue % of GDP" 
       )

tax_rev %>% 
  mutate(highlight_type = case_when(country %in%
                                 c("India","Singapore","Malaysia","Norway",
                                   "Denmark","United States","United Kingdom","China") ~ "Yes",
                               TRUE ~ "No")) %>%
ggplot() +
  geom_line(aes(x = year, y = round(tax_revnue_perc_of_gdp,2), col = country), size = 1.1) +
  scale_x_continuous(breaks = seq(from = 1980, to = 2020, by = 5)) +
  scale_y_continuous(labels = label_dollar(prefix = "", suffix = " %"),
                     breaks = seq(from = 0, to = 60, by = 5)) +
  gghighlight(highlight_type == "Yes",
              unhighlighted_params = list(size = 1, colour = alpha("#ffaa33", 0.4))) +
  facet_wrap(~continent) +
  theme_viny_bright() +
  theme(axis.text.x = element_text(angle = 90)
          ) +
  labs(title = "Total Tax Revenue earned % of GDP for world countries across time",
       subtitle = "created by ViSa",
       caption = "Data Source: Gapminder",
       y = "Total Tax Revenue % of GDP" 
       )

2.3 user defined function

udf_tax_rev_plot <- function(background_line_color = grey){
  
  background_line_color = enquo(background_line_color)

  tax_rev %>% 
    mutate(highlight_type = case_when(country %in%
                                   c("India","Singapore","Malaysia","Norway",
                                     "Denmark","United States","United Kingdom","China") ~ "Yes",
                                 TRUE ~ "No")) %>%
  ggplot() +
    geom_line(aes(x = year, y = round(tax_revnue_perc_of_gdp,2), col = country), size = 1.1) +
    scale_x_continuous(breaks = seq(from = 1980, to = 2020, by = 5)) +
    scale_y_continuous(labels = label_dollar(prefix = "", suffix = " %"),
                       breaks = seq(from = 0, to = 60, by = 5)) +
    gghighlight(highlight_type == "Yes",
                unhighlighted_params = list(size = 1, colour = alpha(background_line_color, 0.4))) +
    facet_wrap(~continent) +
    theme_viny_bright() +
    theme(axis.text.x = element_text(angle = 90)
            ) +
    labs(title = "Total Tax Revenue earned % of GDP for world countries across time",
         subtitle = "created by ViSa",
         caption = "Data Source: Gapminder",
         y = "Total Tax Revenue % of GDP" 
         )
}

udf_tax_rev_plot(pink)

Error: Unknown colour name: ~

udf_tax_rev_plot <- function(background_line_color = grey){
  
  background_line_color = enquo(background_line_color)
  
  print(as_label(background_line_color) )


}

udf_tax_rev_plot("#33ffff")  #33ffff

[1] "\"#33ffff\""

attach(gapminder)

country_highlight_plot <- function(df = gapminder, y_var = gdpPercap, 
                                   background_line_color = "grey", 
                                   countries = default_list 
                                   ){
  
  # default list of highlight countries
  default_list = c("India","Singapore","Malaysia","Norway",
                                     "Denmark","United States","United Kingdom","China")
  
  # quoting y-axis variable
  y_var = enquo(y_var)

  # Data Prep.
  df %>% 
    mutate(highlight_type = case_when(country %in% countries ~ "Yes",
                                      TRUE ~ "No")) %>%
  # Plotting  
  ggplot() +
    geom_line(aes(x = year, y = round(!!y_var,2), col = country), size = 1.1) +
    
    # scale_x_continuous(breaks = seq(from = 1980, to = 2020, by = 5)) +
    # scale_y_continuous(labels = label_dollar(prefix = "", suffix = " %"),
    #                    breaks = seq(from = 0, to = 60, by = 5)) +
    
    gghighlight(highlight_type == "Yes",
                unhighlighted_params = list(size = 1, colour = alpha(background_line_color, 0.4))) +
    # facet_wrap(~continent) +
    
    theme_viny_bright() +
    theme(axis.text.x = element_text(angle = 90)
            ) +
    
    labs(title = "GDP/Cap for world countries across time",
         subtitle = "created by ViSa",
         caption = "Data Source: Gapminder",
         y = "Total Tax Revenue % of GDP" 
         )
}

country_highlight_plot(df = gap_longer, countries = c("Australia","Singapore"), background_line_color = "pink")

2.4 ggcharts lib for dumbell plot

getting issues with this

library(ggcharts)

head(gapminder_new)

data("popeurope")

head(popeurope)

popeurope %>% 
  filter(country %in% c("India","Singapore","Malaysia","Norway",
                        "Denmark","United States","United Kingdom","China")) %>% 
  ggcharts::dumbbell_chart(x = country,
                           y1 = pop1952,
                           y2 = pop2007,
                           top_n = 10,
                           point_colors = c("lightgray","orange")
                            ) +
   scale_y_continuous(
    limits = c(0, NA),
    labels = function(x) paste(x, "Mn.")
  ) +
  theme_ng()

dumbbell_chart(
  data = popeurope,
  x = country,
  y1 = pop1952,
  y2 = pop2007,
  top_n = 10,
  point_colors = c("lightgray", "#494F5C")
) +
  labs(
    x = NULL,
    y = "Population",
    title = "Europe's Largest Countries by Population in 2007"
  ) +
  scale_y_continuous(
    limits = c(0, NA),
    labels = function(x) paste(x, "Mn.")
  )

gapminder_new %>% 
  select(country, "2010", "2019") %>% head() 

2.5 ggalt for dumbell plots

# devtools::install_github('bbc/bbplot')

library(ggalt)
library(bbplot)

gapminder_new %>% 
  select(country, "2010", "2019") %>% 
  mutate(gap = "2019" - "2010") %>% head() 

Error: Problem with `mutate()` input `gap`.
x non-numeric argument to binary operator
i Input `gap` is `"2019" - "2010"`.
Run `rlang::last_error()` to see where the error occurred.

gapminder %>%
  filter(year == 1967 | year == 2007) %>%
  select(country, year, lifeExp) %>%
  spread(year, lifeExp) %>%
  mutate(gap = `2007` - `1967`) %>%
  arrange(desc(gap)) %>%
  head(10)

gapminder_new %>% 
  filter(country %in% c("India","Singapore","Malaysia","Norway",
                        "Denmark","United States","United Kingdom","China")) %>% 
  select(country, "2010", "2019") %>% 
  mutate(gap = .[["2019"]] - .[["2010"]]) %>%
  arrange(desc(gap)) %>%
  
  ggplot(aes(x = .[["2010"]], xend = .[["2019"]], 
         y = reorder(country, gap), group = country)) +
  geom_dumbbell(colour = "#dddddd", size = 2,
                colour_x = "grey", colour_xend = "#FAAB18") +
  bbc_style()

gapminder_new %>% 
  filter(country %in% c("India","Singapore","Malaysia","Norway",
                        "Denmark","United States","United Kingdom","China")) %>% 
  select(country, "1970", "2019") %>% 
  mutate(gap = .[["2019"]] - .[["1970"]]) %>% 
  arrange(desc(gap)) %>%

  ggplot(aes(x = .[["1970"]], xend = .[["2019"]],
         y = reorder(country, gap), group = country)) +
  geom_dumbbell(colour = "#dddddd", size = 2,
                colour_x = "grey", colour_xend = "#FAAB18") +
  bbc_style()

head(gap_longer)

gap_longer %>%
  group_by(continent) %>% 
  filter(country == top_n(x=.,n=5,wt=gdpPercap) %>% select(country))

Error: Problem with `filter()` input `..1`.
x Input `..1` must be of size 2940 or 1, not size 30.
i Input `..1` is `country == top_n(x = ., n = 5, wt = gdpPercap) %>% select(country)`.
i The error occurred in group 1: continent = "Africa".
Run `rlang::last_error()` to see where the error occurred.

Below code gives top 5 countries by gdpPercap across the years

Overall_top5 <- gap_longer %>% 
  group_by(continent, country) %>% 
  summarise(gdpPercap = max(gdpPercap, na.rm = T)) %>% 
  top_n(n = 5, wt = gdpPercap) %>% 
  ungroup()

Overall_top5

Below code gives top 5 countries by gdpPercap of each continent across the years

gap_longer %>% 
  filter(
         country %in% (Overall_top5 %>% pull(country))) %>% 
  ggplot(aes(x = year, y = gdpPercap, color = country)) +
  geom_line() +
  facet_wrap(~continent) +
  theme_viny_bright() +
  theme(legend.position = "none",
        axis.text.x = element_text(angle = 90))

Overall_top5 %>% select(country)

gap_longer %>% 
  filter(year == 2019,
         country %in% (Overall_top5 %>% pull(country)))

gap_longer %>% 
  filter(year == 2019,
         country %in% Overall_top5$country ) 

NA

gap_longer %>% 
  filter(
    year == 2019,
    country %in% (Overall_top5 %>% pull(country))
  )

gap_longer %>% 
    filter(year == 2019, country %in% Overall_top5) 

gap_longer %>% 
    filter(year == 2019, country %in% Overall_top5) %>% 
    pull(country)

character(0)

gap_longer %>% 
    filter(year == 2019, country %in% Overall_top5$country) %>% 
    select(country)

top5_by_continents <- gap_longer %>% 
    filter(year == 2019, country %in% Overall_top5$country) %>% 
    pull(country)

top5_by_continents

 [1] "Australia"            "Botswana"             "Canada"               "Chile"               
 [5] "Denmark"              "Equatorial Guinea"    "Gabon"                "Ireland"             
 [9] "Israel"               "Japan"                "Kuwait"               "Libya"               
[13] "Liechtenstein"        "Luxembourg"           "Mauritius"            "Monaco"              
[17] "New Zealand"          "Norway"               "San Marino"           "Saudi Arabia"        
[21] "Singapore"            "Sweden"               "Switzerland"          "Trinidad and Tobago" 
[25] "United Arab Emirates" "United States"        "Venezuela"           

gap_longer %>% 
  mutate(highlight_type = case_when(country %in% top5_by_continents ~ "Yes",
                                                 TRUE ~ "No"))  %>% 
  #filter(!is.na(continent)) %>% filter(!is.na(gdpPercap)) %>% #head()
  na.exclude %>% 
  ggplot() +
  geom_line(aes(x = year, y = gdpPercap, col = country), size = 1.1) +
  gghighlight(highlight_type == "Yes", 
              unhighlighted_params = list(size = 1, colour = alpha("grey", 0.4))) +
  facet_wrap(~continent) +
  theme_minimal() +
  theme(axis.text.x = element_text(angle = 60),
        legend.position = "none")

tax_rev %>% 
  mutate(highlight_type = case_when(country %in%
                                 c("India","Singapore","Malaysia","Norway",
                                   "Denmark","United States","United Kingdom","China") ~ "Yes",
                               TRUE ~ "No")) %>%
  ggplot() +
  geom_line(aes(x = year, y = tax_revnue_perc_of_gdp, col = as.factor(country)), size = 1.1) +
  gghighlight(highlight_type == "Yes", 
              unhighlighted_params = list(size = 1, colour = alpha("grey", 0.4))) +
  facet_wrap(~continent) +
  theme_minimal() +
  theme(axis.text.x = element_text(angle = 60),
        legend.position = "none")

gap_longer %>% 
  mutate(highlight_type = case_when(country %in% top5_by_continents ~ "Yes",
                                                 TRUE ~ "No"))  %>% 
  #filter(!is.na(continent)) %>% filter(!is.na(gdpPercap)) %>% #head()
  na.exclude %>% summary()

   country               year        gdpPercap        continent    highlight_type    
 Length:6700        Min.   :1960   Min.   :  132   Africa  :2473   Length:6700       
 Class :character   1st Qu.:1978   1st Qu.:  910   Americas:1403   Class :character  
 Mode  :character   Median :1993   Median : 3135   Asia    :1318   Mode  :character  
                    Mean   :1992   Mean   : 9938   Europe  :1396                     
                    3rd Qu.:2006   3rd Qu.:12400   Oceania : 110                     
                    Max.   :2019   Max.   :92600                                     

tax_rev %>% 
  mutate(highlight_type = case_when(country %in%
                                 c("India","Singapore","Malaysia","Norway",
                                   "Denmark","United States","United Kingdom","China") ~ "Yes",
                               TRUE ~ "No")) %>%
  summary()

   country              Code                year      tax_revnue_perc_of_gdp    continent   
 Length:5318        Length:5318        Min.   :1980   Min.   : 0.08581       Africa  :1309  
 Class :character   Class :character   1st Qu.:1993   1st Qu.:11.63091       Americas: 722  
 Mode  :character   Mode  :character   Median :2002   Median :18.01959       Asia    : 749  
                                       Mean   :2001   Mean   :20.05868       Europe  : 926  
                                       3rd Qu.:2009   3rd Qu.:27.63104       Oceania :  75  
                                       Max.   :2017   Max.   :56.91614       NA's    :1537  
 highlight_type    
 Length:5318       
 Class :character  
 Mode  :character  
                   
                   
                   

3 plotly highlight charts

from:

https://stackoverflow.com/questions/64385240/is-there-a-way-to-have-a-highlighted-chart-as-well-as-have-interactivity-of-sele?noredirect=1#comment113856801_64385240

https://plotly-r.com/client-side-linking.html#filter

library(plotly)

# from ggplot2 library

data("txhousing")

txhousing %>% glimpse()

Rows: 8,602
Columns: 9
$ city      <chr> "Abilene", "Abilene", "Abilene", "Abilene", "Abilene", "Abilene", "Abilene", "Abil...
$ year      <int> 2000, 2000, 2000, 2000, 2000, 2000, 2000, 2000, 2000, 2000, 2000, 2000, 2001, 2001...
$ month     <int> 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 1, 2...
$ sales     <dbl> 72, 98, 130, 98, 141, 156, 152, 131, 104, 101, 100, 92, 75, 112, 118, 105, 150, 13...
$ volume    <dbl> 5380000, 6505000, 9285000, 9730000, 10590000, 13910000, 12635000, 10710000, 761500...
$ median    <dbl> 71400, 58700, 58100, 68600, 67300, 66900, 73500, 75000, 64500, 59300, 70900, 65000...
$ listings  <dbl> 701, 746, 784, 785, 794, 780, 742, 765, 771, 764, 721, 658, 779, 700, 738, 810, 77...
$ inventory <dbl> 6.3, 6.6, 6.8, 6.9, 6.8, 6.6, 6.2, 6.4, 6.5, 6.6, 6.2, 5.7, 6.8, 6.0, 6.4, 7.0, 6....
$ date      <dbl> 2000.000, 2000.083, 2000.167, 2000.250, 2000.333, 2000.417, 2000.500, 2000.583, 20...

txhousing %>%  head()

tx <- highlight_key(txhousing, ~city)

base <- plot_ly(tx, color = I("grey")) %>% 
  group_by(city)

time_series <- base %>% 
                  group_by(city) %>% 
                  add_lines(x = ~date, y = ~median)

highlight(
  time_series,
  on = "plotly_hover",
  selectize = FALSE,
  dynamic = FALSE,
  color = "red",
  persistent = FALSE
)

Error in dirname(to) : path too long

plotly_1 <- gap_longer %>% 
  filter(continent == "Asia") %>% 
  na.exclude() %>% 
  
  plotly::highlight_key(., ~country)

base <- plot_ly(plotly_1, color = I("grey")) %>% 
  group_by(country)

time_series <- base %>% 
              group_by(country) %>% 
              add_lines(x = ~year, y = ~gdpPercap)

highlight(
  time_series,
  on = "plotly_hover",
  selectize = FALSE,
  dynamic = FALSE,
  color = "red",
  persistent = FALSE
)

Error in dirname(to) : path too long

plotly_1 <- gap_longer %>% 
  filter(continent == "Asia", gdpPercap < max(20000)) %>% 
  na.exclude() %>% 
  
  plotly::highlight_key(., ~country)

base <- plot_ly(plotly_1, color = I("grey")) %>% 
  group_by(country)

tme_series <- base %>% 
              group_by(country) %>% 
              add_lines(x = ~year, y = ~gdpPercap)

highlight(
  time_series,
  on = "plotly_click",
  selectize = TRUE,
  dynamic = TRUE,
  color = "red",
  persistent = TRUE
)

Error in dirname(to) : path too long

hist <- add_histogram(
  base,
  x = ~gdpPercap,
  histnorm = "probability density"
)

subplot(time_series, hist, nrows = 2) %>% 
  layout(barmode = "overlay", showlegend = FALSE) %>% 
  highlight(
    dynamic = TRUE,
    selectize = TRUE,
    color = "red",
    selected = attrs_selected(opacity = 0.3)
  )

Error in dirname(to) : path too long

3.0.1 Trying to subtract row wise

gapminder_new %>% 
  filter(country == c("India","Bangladesh"))

3.0.1.1 failed attempts

gapminder_new %>% 
  filter(country == c("India","Bangladesh")) %>% 
  .[["India",]] - .[["Bangladesh",]]

Error: Subscript can't be missing for tibbles in `[[`.
Run `rlang::last_error()` to see where the error occurred.

gapminder_new %>% 
  filter(country == c("India","Bangladesh")) %>% 
  .["India",] - .["Bangladesh",]

Error: object '.' not found

gapminder_new %>% 
  filter(country == c("India","Bangladesh")) %>% 
  .[country == "India",] - .[country == "Bangladesh",]

Error: Must subset rows with a valid subscript vector.
i Logical subscripts must match the size of the indexed input.
x Input has size 2 but subscript `country == "India"` has size 1704.
Run `rlang::last_error()` to see where the error occurred.

gapminder_new %>% 
  filter(country == c("India","Bangladesh")) %>% 
  .[India,] - .[Bangladesh,]

Error in `[.tbl_df`(., India, ) : object 'India' not found

gapminder_new %>% 
  filter(country == c("India","Bangladesh")) %>% 
  .[[India,]] - .[[Bangladesh,]]

Error: Subscript can't be missing for tibbles in `[[`.
Run `rlang::last_error()` to see where the error occurred.

gapminder_new %>% 
  filter(country == c("India","Bangladesh")) %>% 
  mutate(Diff_result = (. %>% filter(country == "India") ) - (. %>% filter(country == "Bangladesh"))  )

Error: Problem with `mutate()` input `Diff_result`.
x non-numeric argument to binary operator
i Input `Diff_result` is `-...`.
Run `rlang::last_error()` to see where the error occurred.

gapminder_new[country == "India",] - gapminder_new[country == "Bangladesh",]

Error: Must subset rows with a valid subscript vector.
i Logical subscripts must match the size of the indexed input.
x Input has size 191 but subscript `country == "India"` has size 1704.
Run `rlang::last_error()` to see where the error occurred.

gapminder_new[India,] - gapminder_new[Bangladesh,]

Error in `[.tbl_df`(gapminder_new, India, ) : object 'India' not found

gapminder_new %>% 
  filter(country == "India")

rownames(gapminder_new[country == "India",])

Error: Must subset rows with a valid subscript vector.
i Logical subscripts must match the size of the indexed input.
x Input has size 191 but subscript `country == "India"` has size 1704.
Run `rlang::last_error()` to see where the error occurred.

rownames(gapminder_new[country == India,])

Error in `[.tbl_df`(gapminder_new, country == India, ) : 
  object 'India' not found

gapminder_new[country == "India",]

Error: Must subset rows with a valid subscript vector.
i Logical subscripts must match the size of the indexed input.
x Input has size 191 but subscript `country == "India"` has size 1704.
Run `rlang::last_error()` to see where the error occurred.

gapminder_new

rownames(gapminder_new) <- gapminder_new$country

gapminder_new %>%  head()

gapminder_new["India", 2: ncol(gapminder_new)] #- gapminder_new["Bangladesh", ]

gapminder_new[, 2:ncol(gapminder_new)]

3.0.1.2 solution from stackoverflow

https://stackoverflow.com/questions/64410966/how-to-subtract-a-row-from-another-row-in-r

gapminder_new %>% 
  filter(country %in% c("India","Bangladesh")) %>% 
  select(-1) %>% 
  mutate(across(everything(), ~lead(.x) - (.x))) %>% na.omit()

gapminder_new %>% select(-1) %>% mutate(across(everything(), ~lead(.x) - (.x))) %>% na.omit()

gapminder_new %>% 
  filter(country %in% c("India","Bangladesh"))

3.0.1.3 My own solution

test_set <- as.data.frame(gapminder_new)

rownames(test_set) <- test_set$country

head(test_set)

test_set %>%  select(-country)

test_set["India",2:ncol(test_set)] - test_set["Bangladesh",2:ncol(test_set)]

3.0.2 setting toolips / highcharter

from: https://jkunst.com/blog/posts/2019-02-04-using-tooltips-in-unexpected-ways/

library(highcharter)

3.0.2.1 Series chart

gp <- gapminder %>% 
  arrange(desc(year)) %>% 
  distinct(country, .keep_all = TRUE)

head(gp)

gp2 <- gapminder %>% 
  select(country, year, pop) %>% 
  nest(-country) %>% 
  mutate(
    data = map(data, mutate_mapping, hcaes(x = year, y = pop), drop = TRUE),
    data = map(data, list_parse)
  ) %>% 
  rename(ttdata = data)

gp2

gptot <- left_join(gp, gp2, by = "country")

head(gptot)

hchart(
  gptot,
  "point",
  hcaes(x = lifeExp, y = gdpPercap, name = country, 
        size=pop, group=continent, name=country)
) %>% 
  
  hc_yAxis(type = "logarithmic") %>% 
  
  # this is what creates a chart in tooltip
  hc_tooltip(
    useHTML = TRUE,
    headerFormat = "<b>{point.key}</b>",
    pointFormatter = tooltip_chart(accesor = "ttdata")
  ) %>% 
  
  hc_title(text = "Tooltip chart within a Chart") %>% 
  hc_subtitle(text = "(ttchart: population growth)")

3.0.2.1.1 log

gp2_log <- gapminder %>% 
  select(country, year, pop) %>% 
  nest(-country) %>% 
  mutate(
    data = map(data, mutate_mapping, hcaes(x = year, y = log(pop)), drop = TRUE),
    data = map(data, list_parse)
  ) %>% 
  rename(ttdata_log = data)

gp2_log

gptot_log <- left_join(gp, gp2_log, by = "country")

head(gptot_log)

hchart(
  gptot_log,
  "point",
  hcaes(x = lifeExp, y = gdpPercap, name = country, 
        size=pop, group=continent, name=country)
) %>% 
  
  hc_yAxis(type = "logarithmic") %>% 
  
  # this is what creates a chart in tooltip
  hc_tooltip(
    useHTML = TRUE,
    headerFormat = "<b>{point.key}</b>",
    pointFormatter = tooltip_chart(accesor = "ttdata_log")
  ) %>% 
  
  hc_title(text = "Tooltip chart within a Chart") %>% 
  hc_subtitle(text = "(ttchart: log population growth)")

3.0.2.2 donut chart

from: https://jkunst.com/blog/posts/2019-02-04-using-tooltips-in-unexpected-ways/

donutdata <- gp %>% 
  group_by(continent) %>% 
  summarise(pop = sum(pop/1e6) * 1e6)

donutdata

hchart(donutdata, "pie",
       hcaes(name = continent, y = pop), innerSize = 300)

hc <- hchart(
  donutdata2, "pie", hcaes(name = continent, y = pop),
  innerSize = 375
)

hc

hc %>% 
  hc_tooltip(
    useHTML = TRUE,
    headerFormat = "<b>{point.key}</b>",
    pointFormatter = tooltip_chart(
      accesor = "ttdata",
      hc_opts = list(
        chart = list(type = "scatter"),
        credits = list(enabled = FALSE),
        plotOptions = list(scatter = list(marker = list(radius = 2)))
        ),
      height = 225
      ),
    positioner = JS(
      "function () {
      
        /* one of the most important parts! */
        xp =  this.chart.chartWidth/2 - this.label.width/2
        yp =  this.chart.chartHeight/2 - this.label.height/2
      
        return { x: xp, y: yp };
      
      }"),
    shadow = FALSE,
    borderWidth = 0,
    backgroundColor = "transparent",
    hideDelay = 1000
  )